© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 45233
    Prev
    Next
    INDEX
    Explanations

    technical terms or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    业
    0.51
    国际
    0.49
    体验
    0.46
    寔
    0.46
    留学
    0.45
    вер
    0.45
    谥
    0.43
    闰
    0.43
     Spain
    0.42
    空间
    0.42
    POSITIVE LOGITS
    raft
    0.51
     supplement
    0.44
     provenant
    0.44
    until
    0.44
    worthy
    0.42
    zyk
    0.42
     benutzt
    0.42
     gebruikt
    0.41
     utiliz
    0.41
     supplemental
    0.41
    Activations Density 0.005%

    No Known Activations